BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

Surface Evolver Bench leaderboard

As of 6 Nov 2026, the top score on Surface Evolver Bench is 95.0%, shared by Claude Fable 5 and Kimi K3, ahead of GPT-5.6 Sol at 93.1%, across 29 model configurations with a published result (Epoch AI Benchmarking Hub, result dated 9 Jun 2026). Tasks that require writing correct inputs for the Surface Evolver, a niche scientific tool. Surface Evolver Bench is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • Claude Fable 5 and Kimi K3 share the top Surface Evolver Bench score at 95.0% (Epoch AI Benchmarking Hub, 6 Nov 2026).
  • Surface Evolver Bench: Scientific computing with the Surface Evolver package (Epoch AI Benchmarking Hub).
  • 29 model configurations have a published Surface Evolver Bench result on BenchLeader (BenchLeader, 6 Nov 2026).
  • Surface Evolver Bench does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Scientific computing with the Surface Evolver package.

Published by
Epoch AI Benchmarking Hub
Category
Coding
Index weight
Reference only
Models
29
Data as of
6 Nov 2026

CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.

What the test looks like

Tasks that require writing correct inputs for the Surface Evolver, a niche scientific tool.

How it is scored

Mean score, as published.

What to keep in mind

Niche tool; small set.

Top 15
  1. 1Claude Fable 5 (high)95.0%
  2. 2Kimi K395.0%
  3. 3GPT-5.6 Sol (xhigh)93.1%
  4. 4Kimi K3 (max)93.0%
  5. 5GPT-5.5 (high)88.1%
  6. 6Claude Opus 4.8 (high)87.5%
  7. 7GPT-5.6 Terra (xhigh)83.8%
  8. 8GPT-5.5 (medium)81.3%
  9. 9Gemini 3.8 Flash (high)76.9%
  10. 10Grok 4.5 (high)74.4%
  11. 11Claude Opus 4.8 (none)68.1%
  12. 12GPT-5.6 Luna (medium)61.9%
  13. 13Claude Sonnet 5 (medium)60.0%
  14. 14Gemini 3.5 Flash (medium)58.1%
  15. 15GLM 5.2 (high)55.6%
29 of 29
#
1Claude Fable 5high95.0%64.32026-06-09
2Kimi K395.0%59.12026-07-16
3GPT-5.6 Solxhigh93.1%64.22026-07-09
4Kimi K3max93.0%62.12026-07-16
5GPT-5.5high88.1%63.72026-04-23
6Claude Opus 4.8high87.5%60.62026-05-28
7GPT-5.6 Terraxhigh83.8%60.32026-07-09
8GPT-5.5medium81.3%61.02026-04-23
9Gemini 3.8 Flashhigh76.9%62.02026-09-02
10Grok 4.5high74.4%56.92026-07-08
11Claude Opus 4.8no reasoning68.1%–2026-05-28
12GPT-5.6 Lunamedium61.9%50.72026-07-09
13Claude Sonnet 5medium60.0%–2026-06-30
14Gemini 3.5 Flashmedium58.1%61.92026-05-19
15GLM 5.2high55.6%–2026-06-16
16MiniMax M355.0%56.42026-06-01
17GLM 5.3 Flashmax52.5%54.22026-08-20
18Muse Spark 1.1high52.5%–2026-07-09
19Kimi K2.7 Code48.8%54.22026-06-12
20DeepSeek V4.1 Flashhigh46.3%55.72026-09-09
21Qwen3.8 27Bxhigh45.0%52.52026-08-14
22Qwen3.6 35B A3B44.4%46.12026-04-14
23DeepSeek V4 Prohigh40.0%57.52026-04-24
24Gemma 4 31B30.6%47.82026-04-02
25Mistral Large 428.1%52.92026-10-06
26Mistral Medium 3.526.9%46.62026-04-28
27gpt-oss-120b25.0%45.52025-08-05
28Trinity Largethinking15.6%47.12026-04-01
29Laguna M.115.6%37.32026-04-28

More coding benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on Surface Evolver Bench

Cite as: BenchLeader, “Surface Evolver Bench leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/surface_evolver_bench.

Surface Evolver Bench: questions

What does Surface Evolver Bench measure?
Tasks that require writing correct inputs for the Surface Evolver, a niche scientific tool. Scores are reported in percent of tasks solved; higher is better.
What is the top score on Surface Evolver Bench?
As of 6 Nov 2026, the highest score on Surface Evolver Bench is 95.0%, shared by Claude Fable 5 and Kimi K3, ahead of GPT-5.6 Sol at 93.1%. Scores come from Epoch AI Benchmarking Hub and are re-read daily.
Which AI model leads Surface Evolver Bench?
Claude Fable 5 and Kimi K3 tie for first on Surface Evolver Bench at 95.0% as of 6 Nov 2026, ahead of GPT-5.6 Sol at 93.1%.
How many models have Surface Evolver Bench results?
29 model configurations have a Surface Evolver Bench result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
Who runs Surface Evolver Bench and how often is it updated?
Surface Evolver Bench is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
Does Surface Evolver Bench count toward the BenchLeader Index?
No. Surface Evolver Bench is shown for reference but left out of the composite index.